Event Detection and Correlation from Moving Object Sensor Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Rule-based event correlation techniques fail to detect events corresponding to unknown rules and are inadequate in dynamic systems, leading to missed events due to changing causes, resulting in inefficiencies and downtime in complex systems like transportation networks and data centers.
Innovation Solution
A system that uses static and dynamic sensors to detect and correlate events from moving object sensor data, employing online analysis and a hierarchical neighborhood tree to identify events and discover rules, enabling real-time insight into system status and optimizing resource use.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If rule based event correlation is used, then events can be processed and extracted, but events corresponding to unknown rules are missed
Solution Approach 1:
The patent transitions from static rule-based correlation to dynamic correlation by continuously learning from detected events. The system adapts its correlation models over time, allowing it to discover new event patterns and relationships that were not predetermined by fixed rules, thus resolving the contradiction between processing efficiency and detection completeness.
Solution Approach 2:
The system implements feedback mechanisms where detected events are used to refine and update correlation models. By continuously feeding back detected events into the learning process, the system improves its ability to recognize unknown event patterns while maintaining efficient processing through learned optimizations.
2Ease of operation
If rule based event correlation is used, then known event patterns can be identified, but events in dynamic systems with changing causes are missed
Solution Approach 1:
The patent makes the correlation system dynamic by continuously updating models based on detected events. This allows the system to adapt to changing causes and patterns in dynamic environments while maintaining operational simplicity through automated learning processes that require minimal manual intervention.
Solution Approach 2:
The system changes its operational parameters automatically by learning from detected events. Correlation thresholds, patterns, and models are dynamically adjusted based on observed data, enabling the system to adapt to changing system conditions without requiring manual reconfiguration of correlation rules.
3Device complexity
If traditional event correlation methods are used, then processing is straightforward, but real-time insights into system status are insufficient
Solution Approach 1:
The patent segments the correlation process into distinct phases: event detection, event correlation, and insight generation. This segmentation allows each phase to be optimized independently, reducing overall system complexity while improving the quality and timeliness of system status insights through specialized processing at each stage.
Solution Approach 2:
The system introduces intermediate processing layers that transform raw sensor data into correlated events and then into meaningful insights. These intermediary processing stages act as mediators that bridge the gap between simple data collection and complex analysis, enabling real-time insights without requiring overly complex direct processing.
Data Source
AI summary
An exemplary embodiment of the present techniques may detect and correlate events from moving object sensor data by receiving data from a sensor. The data received from the sensor may be mapped, and events may be detected based on the mapped sensor data. Events from the mapped sensor data may be correlated online.